Security readout for executives and security teams
Plain-English summary
LaVague 0.2.35 may execute Python supplied indirectly through hostile web content. A malicious page can influence language-model output, which the affected extractor evaluates on the operator’s computer. Successful exploitation could compromise the confidentiality, integrity, and availability of that host.
Executive priority
Treat exposed LaVague 0.2.35 automation as an immediate containment and remediation priority, especially on hosts holding credentials or production access. Prioritize inventory, isolation, and vendor-guidance review. The critical impact warrants urgency even though active exploitation is not established.
Technical view
The flaw is in PythonFromMarkdownExtractor.extract_as_object. It evaluates untrusted language-model output derived from web content, creating a CWE-94 code-injection path. Exploitation requires indirect prompt injection and successful manipulation of model output; the supplied CVSS 4.0 score is 9.2.
Likely exposure
Exposure is most likely where LaVague 0.2.35 processes attacker-controlled or untrusted webpages and invokes the affected extractor. The bundle does not establish whether other releases are affected, despite inconsistent affected-version metadata, so inventories require careful verification.
Exploitation context
The source bundle describes a viable remote-code-execution condition, but does not report observed exploitation. The CVE is not identified as KEV. Attack complexity is rated high and requires a prompt-injection condition, yet no privileges or user interaction are reflected in the supplied vector.
Researcher notes
The core trust-boundary failure is evaluation of model-generated text influenced by webpage content. The supplied evidence identifies version 0.2.35, while structured affected data lists “0” with default unaffected status; this inconsistency limits version-range conclusions. No fixed release or vendor-endorsed workaround is supplied.
Mitigation direction
- Identify and suspend LaVague 0.2.35 workflows that process untrusted web content.
- Avoid using PythonFromMarkdownExtractor.extract_as_object until vendor guidance is reviewed.
- Run unavoidable automation in isolated, least-privileged environments without sensitive credentials.
- Check the project issue and advisory for an official patch or safe upgrade.
- Restrict outbound access and secrets available to affected automation hosts.
Validation and detection
- Inventory installed LaVague versions and locate deployments running 0.2.35.
- Determine whether workflows invoke PythonFromMarkdownExtractor.extract_as_object.
- Review whether affected workflows process public or attacker-controlled webpages.
- Inspect execution telemetry for unexpected Python activity originating from LaVague processes.
- Confirm remediated workflows no longer evaluate model-generated content as code.
Public sources used
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
CWE-94: Code execution behavior lookup
Code execution and unsafe deserialization weaknesses often justify reviewing execution behavior and process telemetry. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
Open ATT&CK lookupExecution behavior lookup
The CVE wording references code or command execution, so execution technique review may help defensive triage. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.
Open ATT&CK lookupCVE-2026-85694 mapping review
Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.
Open ATT&CK lookup- Severity
- Critical
- CVSS
- 9.2 (4.0)
- Known Exploited
- No
- Published
Vector: CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
CNA and ADP enrichment extracted from CVE v5
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
SSVC decision data
CVSS vector scores
2 official scoresWe collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N——VulnCheckCVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H2.25.9VulnCheckVulnerability scoring details
Base CVSS 4.0 score
9.2CriticalVector: CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Base CVSS 3.1 score
8.1HighVector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
Vulnerability timeline
Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.
- CVE reservedCVE Program
The CVE ID was reserved by the assigning CNA.
- CVE publishedCVE Program
The CVE record was published.
- CVE updatedCVE Program
The CVE record metadata indicates this as the latest update time.
ADP provider summaries
Source materials
- CVE List V5 sourceCVE List V5
- GitHub Issue #650CVE reference, VulnCheck · issue-tracking
- https://github.com/lavague-ai/LaVagueCVE reference, VulnCheck · product
- https://github.com/lavague-ai/LaVague/blob/9024bb83/lavague-core/lavague/core/extractors.pyCVE reference, VulnCheck · technical-description
- VulnCheck Advisory: LaVague 0.2.35 Remote Code Execution via eval extractionCVE reference, VulnCheck · third-party-advisory
Products and packages named in the record
CWE details
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
Improper Control of Generation of Code ('Code Injection')
Improper Control of Generation of Code ('Code Injection') represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.